Pinned Loading

1. idea-to-ship-skills idea-to-ship-skills Public

   Composable Agent Skills (Claude + OpenAI Codex) for taking an idea from fuzzy → validated → sequenced build → shipped — a manual tier (ideate, deep-dive, prompt-pack) and an autonomous tier (autopi…

   Shell 91 7

2. didrun didrun Public

   Flight records for agent-written code — deterministic session capture, evidence ledger, and graded verification. No LLM in the trust path.

   Python 4

3. countershape countershape Public

   A completed autonomous AI build: an agent built this month-long project on its own under a verification discipline where every commit carries cryptographic receipts of what actually ran. All ten un…

   Go 5

4. meridian-meta-control-center meridian-meta-control-center Public

   Open-source AI command center for agency Meta advertising: cross-client KPIs, an AI analyst proposing one-click optimizations, creative intelligence, and designed weekly reports. Demo mode out of t…

   TypeScript

5. prentice prentice Public

   Evidence-aware workflow discovery and optional governed AI-assisted construction

   Shell

6. redline-autopilot-case-study redline-autopilot-case-study Public archive

   Frozen artifact of a ~13.5h autonomous Claude run (idea-to-ship autopilot). Known unfixed SSRF, do not deploy. Case study, not a product.

   TypeScript 7